Download Introduction - Sociologist Statistics - Lecture Slides and more Slides Sociology in PDF only on Docsity! Soci708 – Statistics for Sociologists1 Module 1 – Introduction François Nielsen University of North Carolina Chapel Hill Fall 2008 1Adapted from slides for the course Quantitative Methods in Sociology (Sociology 6Z3) taught at McMaster University by Robert Andersen (now at University of Toronto) 1 / 7 Plots of O-Ring Damage by Launch Temperature 2 / 7 Levels of Measurement A Refined Typology of Levels of Measurement É A categorical (nominal, qualitative) variable is an exclusive & exhaustive set of attributes É E.g. sex or gender, religion, region of the U.S. É An ordinal variable adds an ordering of the categories É E.g. Mohr scale of hardness – categories ordered from graphite to diamond by relation “A scratches B”; Likert scales with categories Strongly Agree to Strongly Disagree É An interval variable adds a constant interval between categories É E.g. temperature in °F or °C degrees; IQ É A ratio variable adds an absolute zero É E.g. temperature in °K degrees, income of individual, GDP of country, age, percentages É Thus one can say “$25,000 is half as much as $50,000” 5 / 7 Implications for Data Analysis É The level of measurement determines the kinds of analysis that can be carried out with a variable É In practice one can simplify the four-fold typology into two categories: É Qualitative variables: É Includes categorical variables + ordinal variables treated as categorical – e.g. age in years recoded into YOUNG, ADULT, SENIOR categories É Analyzed using contingency tables (tabular analysis) É Quantitative variables: É Includes interval variables + ratio variables + ordinal variables treated as interval variables – e.g. “How well do you speak Spanish?” coded from 1 to 5 É Analyzed using scatterplots & regression analysis É There are advanced analytical techniques for ordinal data that are beyond the scope of this class 6 / 7 Three Central Aspects to Statistics 1. Data Production É Designing research (e.g., a survey or an experiment) so that it produces data that help answer important questions É These issues will be topic of Module 5 – Producing Data 2. Data Analysis É Describing data with graphs and numerical summaries É Displaying patterns and trends É Measuring differences 3. Statistical Inference É Using information about a sample of individuals, drawn at random from a larger population, to establish conclusions about characteristics of the population 7 / 7